A topic recommender for journalists

Abstract

The way in which people acquire information on events and form their own opinion on them has changed dramatically with the advent of social media. For many readers, the news gathered from online sources become an opportunity to share points of view and information within micro-blogging platforms such as Twitter, mainly aimed at satisfying their communication needs. Furthermore, the need to deepen the aspects related to news stimulates a demand for additional information which is often met through online encyclopedias, such as Wikipedia. This behaviour has also influenced the way in which journalists write their articles, requiring a careful assessment of what actually interests the readers. The goal of this paper is to present a recommender system, What to Write and Why, capable of suggesting to a journalist, for a given event, the aspects still uncovered in news articles on which the readers focus their interest. The basic idea is to characterize an event according to the echo it receives in online news sources and associate it with the corresponding readers' communicative and informative patterns, detected through the analysis of Twitter and Wikipedia, respectively. Our methodology temporally aligns the results of this analysis and recommends the concepts that emerge as topics of interest from Twitter and Wikipedia, either not covered or poorly covered in the published news articles.

News Article Retrieval in Context for Event-centric Narrative Creation

“…Therefore, future work should aim to find more robust ways to incorporate the temporal aspect in the ranking function [22]. A possible way to achieve that is to identify temporal phenomena such as trending terms or entities in the underlying news article collection [22] or in external sources such as social media [8]. Furthermore, we have found that this task is more challenging when the query event involves entities that appear more frequently in the collection, which we plan to further study in the future.…”

“…Recent work on developing automatic applications to support writers has focused on designing tools that track and filter information from social media to support journalists [11,53]. Cucchiarelli et al [8] track the Twitter stream and Wikipedia edits to suggest potentially interesting topics that relate to a new event that a writer can include in their narrative when reporting on the event. In contrast, instead of relying on external sources, we aim to retrieve news articles that describe events from the past that can help the writer expand the incomplete narrative about a specific event.…”

Forecasting the nearly unforecastable: why aren’t airline bookings adhering to the prediction algorithm?

“…There are contexts in which one may want to serendipitously recommend new items that the user probably will like but may not be aware of based on associated interests and external events [ 16 , 50 ]. With limited exceptions [ 6 , 88 ], there has been sparse research in the serendipity area with large-scale datasets.…”

Predicting the success of news

“…In their methodology component metrics are combined, and journalists are proposed with topics in breaking news situations in which there is an information need (detected from online news, Twitter and Wikipedia), but not relevant supply for aspects not covered by the news media. [15][16][17][18] Considering the methodology, we find the work by Diakopolos et al interesting in the sense that they used a design process to produce a use case of a useful prediction tool to spot eyewitness information from social media, arranging interviews with reporters to understand their use of social media and journalistic information needs before developing the tool [22].…”